© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B-IT
    3. 50-GEMMASCOPE-2-TRANSCODER-262K
    4. 34114
    Prev
    Next
    INDEX
    Explanations

    Ireland

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/transcoder_all/layer_50_width_262k_l0_small_affine
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    喜
    0.44
    പ്പ
    0.43
     stan
    0.42
     clinically
    0.40
    科技有限公司
    0.40
    র্ভাব
    0.39
     bras
    0.39
    ব্র
    0.38
     പൂർ
    0.38
    툐
    0.38
    POSITIVE LOGITS
    Does
    0.40
    Dt
    0.40
     अंज
    0.40
     Gile
    0.39
    Aware
    0.39
    Done
    0.38
    An
    0.38
    宒
    0.38
    DT
    0.37
    انية
    0.37
    Activations Density 0.000%

    No Known Activations